Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Java @Override annotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pha
    0.48
    mark
    0.40
    condition
    0.38
    phal
    0.37
     ":
    0.37
    iota
    0.37
    ißler
    0.36
    tencent
    0.36
    swering
    0.36
    alpha
    0.36
    POSITIVE LOGITS
     maneira
    0.39
    ौरी
    0.38
    앗
    0.38
    椙
    0.38
    بدا
    0.37
    िल्‍
    0.37
     Hyp
    0.37
     immunized
    0.37
    闲
    0.36
     inmun
    0.36
    Act Density 0.002%

    No Known Activations